© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 16347
    Prev
    Next
    INDEX
    Explanations

    rotation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     нанес
    -0.09
     harina
    -0.08
     Printed
    -0.08
    /pdf
    -0.08
    可信
    -0.08
    urun
    -0.08
     nais
    -0.08
     сказала
    -0.08
     Produk
    -0.07
     aplicada
    -0.07
    POSITIVE LOGITS
     rotates
    0.11
     घूम
    0.11
     rotating
    0.11
     orbit
    0.10
     rotation
    0.10
     rotational
    0.10
     cyclic
    0.10
    orbit
    0.10
    _rotation
    0.09
    rotation
    0.09
    Activations Density 0.007%

    No Known Activations